Researchers at the Tokyo Institute of Technology (Tokyo Tech) have pioneered a wrist-worn device for 3D hand pose estimation, using a camera that captures images of the back of the hand, supported by a neural network (DorsalNet) to recognise dynamic gestures.
The system was developed by researchers at the Tokyo Institute of Technology alongside researchers at Carnegie Mellon University, the University of St Andrews and the University of New South Wales.
Conventionally, haptic gloves have been used to track hand gestures, the bulky nature of which carries the risk of obscuring subtle hand gestures.
The research team, led by Hideki Koke at Tokyo Tech, created the camera-based wrist-worn 3D hand pose recognition system which can capture hand motions in mobile settings, as Koke explained: "This work is the first vision-based real-time 3D hand pose estimator using visual features from the dorsal hand region,"
The system consists of a camera supported by a neural network named DorsalNet which can accurately estimate 3D hand poses by detecting changes in the back of the hand.
The development could be used to advance the development of controllers supporting bare-hand interaction, with the researchers demonstrating that the system can be used for smart devices control, with potential to be used as a virtual mouse or keyboard by rotating the wrist to control the position of the pointer with an eight-key keyboard for typing input.